#include "diff.h"
#include "diffcore.h"
#include "delta.h"
+#include "count-delta.h"
/* Table of rename/copy destinations */
if (first < rename_dst_nr)
memmove(rename_dst + first + 1, rename_dst + first,
(rename_dst_nr - first - 1) * sizeof(*rename_dst));
- rename_dst[first].two = two;
+ rename_dst[first].two = alloc_filespec(two->path);
+ fill_filespec(rename_dst[first].two, two->sha1, two->mode);
rename_dst[first].pair = NULL;
return &(rename_dst[first]);
}
+/* Table of rename/copy src files */
static struct diff_rename_src {
struct diff_filespec *one;
- unsigned src_used : 1;
+ unsigned src_path_left : 1;
} *rename_src;
static int rename_src_nr, rename_src_alloc;
-static struct diff_rename_src *locate_rename_src(struct diff_filespec *one,
- int insert_ok)
+static struct diff_rename_src *register_rename_src(struct diff_filespec *one,
+ int src_path_left)
{
int first, last;
}
first = next+1;
}
- /* not found */
- if (!insert_ok)
- return NULL;
+
/* insert to make it at "first" */
if (rename_src_alloc <= rename_src_nr) {
rename_src_alloc = alloc_nr(rename_src_alloc);
memmove(rename_src + first + 1, rename_src + first,
(rename_src_nr - first - 1) * sizeof(*rename_src));
rename_src[first].one = one;
- rename_src[first].src_used = 0;
+ rename_src[first].src_path_left = src_path_left;
return &(rename_src[first]);
}
if (src->sha1_valid && dst->sha1_valid &&
!memcmp(src->sha1, dst->sha1, 20))
return 1;
- if (diff_populate_filespec(src) || diff_populate_filespec(dst))
- /* this is an error but will be caught downstream */
+ if (diff_populate_filespec(src, 1) || diff_populate_filespec(dst, 1))
+ return 0;
+ if (src->size != dst->size)
+ return 0;
+ if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
return 0;
if (src->size == dst->size &&
!memcmp(src->data, dst->data, src->size))
int src; /* index in rename_src */
int dst; /* index in rename_dst */
int score;
- int rank;
};
static int estimate_similarity(struct diff_filespec *src,
* dst, and then some edit has been applied to dst.
*
* Compare them and return how similar they are, representing
- * the score as an integer between 0 and 10000, except
- * where they match exactly it is considered better than anything
- * else.
+ * the score as an integer between 0 and MAX_SCORE.
+ *
+ * When there is an exact match, it is considered a better
+ * match than anything else; the destination does not even
+ * call into this function in that case.
*/
void *delta;
- unsigned long delta_size, base_size;
+ unsigned long delta_size, base_size, src_copied, literal_added;
+ unsigned long delta_limit;
int score;
/* We deal only with regular files. Symlink renames are handled
/* We would not consider edits that change the file size so
* drastically. delta_size must be smaller than
* (MAX_SCORE-minimum_score)/MAX_SCORE * min(src->size, dst->size).
+ *
* Note that base_size == 0 case is handled here already
* and the final score computation below would not have a
* divide-by-zero issue.
if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
+ if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
+ return 0; /* error but caught downstream */
+
+ delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
delta = diff_delta(src->data, src->size,
dst->data, dst->size,
- &delta_size);
- /*
- * We currently punt here, but we may later end up parsing the
- * delta to really assess the extent of damage. A big consecutive
- * remove would produce small delta_size that affects quite a
- * big portion of the file.
+ &delta_size, delta_limit);
+ if (!delta)
+ /* If delta_limit is exceeded, we have too much differences */
+ return 0;
+
+ /* A delta that has a lot of literal additions would have
+ * big delta_size no matter what else it does.
*/
+ if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
+ return 0;
+
+ /* Estimate the edit size by interpreting delta. */
+ if (count_delta(delta, delta_size, &src_copied, &literal_added)) {
+ free(delta);
+ return 0;
+ }
free(delta);
+ /* Extent of damage */
+ if (src->size + literal_added < src_copied)
+ delta_size = 0;
+ else
+ delta_size = (src->size - src_copied) + literal_added;
+
/*
* Now we will give some score to it. 100% edit gets 0 points
* and 0% edit gets MAX_SCORE points.
return score;
}
-static void record_rename_pair(struct diff_queue_struct *renq,
- int dst_index, int src_index, int score)
+static void record_rename_pair(int dst_index, int src_index, int score)
{
struct diff_filespec *one, *two, *src, *dst;
struct diff_filepair *dp;
two = alloc_filespec(dst->path);
fill_filespec(two, dst->sha1, dst->mode);
- dp = diff_queue(renq, one, two);
+ dp = diff_queue(NULL, one, two);
dp->score = score;
-
- rename_src[src_index].src_used = 1;
+ dp->source_stays = rename_src[src_index].src_path_left;
rename_dst[dst_index].pair = dp;
}
/*
* We sort the rename similarity matrix with the score, in descending
- * order (more similar first).
+ * order (the most similar first).
*/
static int score_compare(const void *a_, const void *b_)
{
return b->score - a->score;
}
-int diff_scoreopt_parse(const char *opt)
+static int compute_stays(struct diff_queue_struct *q,
+ struct diff_filespec *one)
{
- int diglen, num, scale, i;
- if (opt[0] != '-' || (opt[1] != 'M' && opt[1] != 'C'))
- return -1; /* that is not a -M nor -C option */
- diglen = strspn(opt+2, "0123456789");
- if (diglen == 0 || strlen(opt+2) != diglen)
- return 0; /* use default */
- sscanf(opt+2, "%d", &num);
- for (i = 0, scale = 1; i < diglen; i++)
- scale *= 10;
-
- /* user says num divided by scale and we say internally that
- * is MAX_SCORE * num / scale.
- */
- return MAX_SCORE * num / scale;
+ int i;
+ for (i = 0; i < q->nr; i++) {
+ struct diff_filepair *p = q->queue[i];
+ if (strcmp(one->path, p->two->path))
+ continue;
+ if (DIFF_PAIR_RENAME(p)) {
+ return 0; /* something else is renamed into this */
+ }
+ }
+ return 1;
}
-void diffcore_rename(int detect_rename, int minimum_score)
+void diffcore_rename(struct diff_options *options)
{
+ int detect_rename = options->detect_rename;
+ int minimum_score = options->rename_score;
+ int rename_limit = options->rename_limit;
struct diff_queue_struct *q = &diff_queued_diff;
- struct diff_queue_struct renq, outq;
+ struct diff_queue_struct outq;
struct diff_score *mx;
- int i, j;
+ int i, j, rename_count;
int num_create, num_src, dst_cnt;
if (!minimum_score)
- minimum_score = DEFAULT_MINIMUM_SCORE;
- renq.queue = NULL;
- renq.nr = renq.alloc = 0;
+ minimum_score = DEFAULT_RENAME_SCORE;
+ rename_count = 0;
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
continue; /* unmerged */
else
locate_rename_dst(p->two, 1);
- else if (!DIFF_FILE_VALID(p->two))
- locate_rename_src(p->one, 1);
- else if (1 < detect_rename) /* find copy, too */
- locate_rename_src(p->one, 1);
+ else if (!DIFF_FILE_VALID(p->two)) {
+ /* If the source is a broken "delete", and
+ * they did not really want to get broken,
+ * that means the source actually stays.
+ */
+ int stays = (p->broken_pair && !p->score);
+ register_rename_src(p->one, stays);
+ }
+ else if (detect_rename == DIFF_DETECT_COPY)
+ register_rename_src(p->one, 1);
}
- if (rename_dst_nr == 0)
+ if (rename_dst_nr == 0 ||
+ (0 < rename_limit && rename_limit < rename_dst_nr))
goto cleanup; /* nothing to do */
/* We really want to cull the candidates list early
struct diff_filespec *one = rename_src[j].one;
if (!is_exact_match(one, two))
continue;
- record_rename_pair(&renq, i, j, MAX_SCORE);
+ record_rename_pair(i, j, MAX_SCORE);
+ rename_count++;
break; /* we are done with this entry */
}
}
- diff_debug_queue("done detecting exact", &renq);
/* Have we run out the created file pool? If so we can avoid
* doing the delta matrix altogether.
*/
- if (renq.nr == rename_dst_nr)
- goto flush_rest;
+ if (rename_count == rename_dst_nr)
+ goto cleanup;
+
+ if (minimum_score == MAX_SCORE)
+ goto cleanup;
- num_create = (rename_dst_nr - renq.nr);
+ num_create = (rename_dst_nr - rename_count);
num_src = rename_src_nr;
mx = xmalloc(sizeof(*mx) * num_create * num_src);
for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
if (dst->pair)
continue; /* already done, either exact or fuzzy. */
if (mx[i].score < minimum_score)
- break; /* there is not any more diffs applicable. */
- record_rename_pair(&renq, mx[i].dst, mx[i].src, mx[i].score);
+ break; /* there is no more usable pair. */
+ record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
+ rename_count++;
}
free(mx);
- diff_debug_queue("done detecting fuzzy", &renq);
- flush_rest:
+ cleanup:
/* At this point, we have found some renames and copies and they
- * are kept in renq. The original list is still in *q.
- *
- * Scan the original list and move them into the outq; we will sort
- * outq and swap it into the queue supplied to pass that to
- * downstream, so we assign the sort keys in this loop.
- *
- * See comments at the top of record_rename_pair for numbers used
- * to assign rename_rank.
+ * are recorded in rename_dst. The original list is still in *q.
*/
outq.queue = NULL;
outq.nr = outq.alloc = 0;
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
- struct diff_rename_src *src = locate_rename_src(p->one, 0);
- struct diff_rename_dst *dst = locate_rename_dst(p->two, 0);
struct diff_filepair *pair_to_free = NULL;
- if (dst) {
- /* creation */
- if (dst->pair) {
- /* renq has rename/copy already to produce
- * this file, so we do not emit the creation
- * record in the output.
- */
+ if (!DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
+ /*
+ * Creation
+ *
+ * We would output this create record if it has
+ * not been turned into a rename/copy already.
+ */
+ struct diff_rename_dst *dst =
+ locate_rename_dst(p->two, 0);
+ if (dst && dst->pair) {
diff_q(&outq, dst->pair);
pair_to_free = p;
}
else
- /* no matching rename/copy source, so record
- * this as a creation.
+ /* no matching rename/copy source, so
+ * record this as a creation.
*/
diff_q(&outq, p);
}
- else if (!diff_unmodified_pair(p))
- /* all the other cases need to be recorded as is */
- diff_q(&outq, p);
- else {
- /* unmodified pair needs to be recorded only if
- * it is used as the source of rename/copy
+ else if (DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two)) {
+ /*
+ * Deletion
+ *
+ * We would output this delete record if:
+ *
+ * (1) this is a broken delete and the counterpart
+ * broken create remains in the output; or
+ * (2) this is not a broken delete, and rename_dst
+ * does not have a rename/copy to move p->one->path
+ * out of existence.
+ *
+ * Otherwise, the counterpart broken create
+ * has been turned into a rename-edit; or
+ * delete did not have a matching create to
+ * begin with.
*/
- if (src && src->src_used)
- diff_q(&outq, p);
+ if (DIFF_PAIR_BROKEN(p)) {
+ /* broken delete */
+ struct diff_rename_dst *dst =
+ locate_rename_dst(p->one, 0);
+ if (dst && dst->pair)
+ /* counterpart is now rename/copy */
+ pair_to_free = p;
+ }
+ else {
+ for (j = 0; j < rename_dst_nr; j++) {
+ if (!rename_dst[j].pair)
+ continue;
+ if (strcmp(rename_dst[j].pair->
+ one->path,
+ p->one->path))
+ continue;
+ break;
+ }
+ if (j < rename_dst_nr)
+ /* this path remains */
+ pair_to_free = p;
+ }
+
+ if (pair_to_free)
+ ;
else
- pair_to_free = p;
- }
- if (pair_to_free) {
- diff_free_filespec_data(pair_to_free->one);
- diff_free_filespec_data(pair_to_free->two);
- free(pair_to_free);
+ diff_q(&outq, p);
}
+ else if (!diff_unmodified_pair(p))
+ /* all the usual ones need to be kept */
+ diff_q(&outq, p);
+ else
+ /* no need to keep unmodified pairs */
+ pair_to_free = p;
+
+ if (pair_to_free)
+ diff_free_filepair(pair_to_free);
}
diff_debug_queue("done copying original", &outq);
- free(renq.queue);
free(q->queue);
*q = outq;
diff_debug_queue("done collapsing", q);
- cleanup:
+ /* We need to see which rename source really stays here;
+ * earlier we only checked if the path is left in the result,
+ * but even if a path remains in the result, if that is coming
+ * from copying something else on top of it, then the original
+ * source is lost and does not stay.
+ */
+ for (i = 0; i < q->nr; i++) {
+ struct diff_filepair *p = q->queue[i];
+ if (DIFF_PAIR_RENAME(p) && p->source_stays) {
+ /* If one appears as the target of a rename-copy,
+ * then mark p->source_stays = 0; otherwise
+ * leave it as is.
+ */
+ p->source_stays = compute_stays(q, p->one);
+ }
+ }
+
+ for (i = 0; i < rename_dst_nr; i++) {
+ diff_free_filespec_data(rename_dst[i].two);
+ free(rename_dst[i].two);
+ }
+
free(rename_dst);
rename_dst = NULL;
rename_dst_nr = rename_dst_alloc = 0;